注意

您正在阅读 MMEditing 0.x。 MMEditing 0.x 会在 2022 年末开始逐步停止维护，建议您及时升级到 MMEditing 1.0 版本，享受由 OpenMMLab 2.0 带来的更多新特性和更佳的性能表现。阅读 MMEditing 1.0 的发版日志、代码和文档以了解更多。

补全模型¶

AOT-GAN (TVCG’2021)¶

AOT-GAN: Aggregated Contextual Transformations for High-Resolution Image Inpainting

摘要¶

结果与模型¶

Places365-Challenge

算法	掩膜类型	分辨率	训练集容量	测试集	l1 损失	PSNR	SSIM	下载
AOT-GAN	free-form (50-60%)	512x512	500k	Places365-val	7.07	19.01	0.682	模型 \| 日志

评估指标	掩膜缺损	论文结果	复现结果
L1 (10^-2)	1 – 10%	0.55	0.54
(lower better)	10 – 20%	1.19	1.47
	20 – 30%	2.11	2.79
	30 – 40%	3.20	4.38
	40 – 50%	4.51	6.28
	50 – 60%	7.07	10.16
PSNR	1 – 10%	34.79	inf
(higher better)	10 – 20%	29.49	31.22
	20 – 30%	26.03	27.65
	30 – 40%	23.58	25.06
	40 – 50%	21.65	23.01
	50 – 60%	19.01	20.05
SSIM	1 – 10%	0.976	0.982
(higher better)	10 – 20%	0.940	0.951
	20 – 30%	0.890	0.911
	30 – 40%	0.835	0.866
	40 – 50%	0.773	0.815
	50 – 60%	0.682	0.739

引用¶

@inproceedings{yan2021agg,
  author = {Zeng, Yanhong and Fu, Jianlong and Chao, Hongyang and Guo, Baining},
  title = {Aggregated Contextual Transformations for High-Resolution Image Inpainting},
  booktitle = {Arxiv},
  pages={-},
  year = {2020}
}

DeepFillv1 (CVPR’2018)¶

DeepFillv1 (CVPR'2018)

@inproceedings{yu2018generative,
  title={Generative image inpainting with contextual attention},
  author={Yu, Jiahui and Lin, Zhe and Yang, Jimei and Shen, Xiaohui and Lu, Xin and Huang, Thomas S},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={5505--5514},
  year={2018}
}

Places365-Challenge

算法	掩膜类型	分辨率	训练集容量	测试集	l1 损失	PSNR	SSIM	下载
DeepFillv1	square bbox	256x256	3500k	Places365-val	11.019	23.429	0.862	模型 \| 日志

CelebA-HQ

算法	掩膜类型	分辨率	训练集容量	测试集	l1 损失	PSNR	SSIM	下载
DeepFillv1	square bbox	256x256	1500k	CelebA-val	6.677	26.878	0.911	模型 \| 日志

DeepFillv2 (CVPR’2019)¶

DeepFillv2 (CVPR'2019)

@inproceedings{yu2019free,
  title={Free-form image inpainting with gated convolution},
  author={Yu, Jiahui and Lin, Zhe and Yang, Jimei and Shen, Xiaohui and Lu, Xin and Huang, Thomas S},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={4471--4480},
  year={2019}
}

Places365-Challenge

算法	掩膜类型	分辨率	训练集容量	测试集	l1 损失	PSNR	SSIM	下载
DeepFillv2	free-form	256x256	100k	Places365-val	8.635	22.398	0.815	模型 \| 日志

CelebA-HQ

算法	掩膜类型	分辨率	训练集容量	测试集	l1 损失	PSNR	SSIM	下载
DeepFillv2	free-form	256x256	20k	CelebA-val	5.411	25.721	0.871	模型 \| 日志

Global&Local (ToG’2017)¶

Global&Local (ToG'2017)

@article{iizuka2017globally,
  title={Globally and locally consistent image completion},
  author={Iizuka, Satoshi and Simo-Serra, Edgar and Ishikawa, Hiroshi},
  journal={ACM Transactions on Graphics (ToG)},
  volume={36},
  number={4},
  pages={1--14},
  year={2017},
  publisher={ACM New York, NY, USA}
}

请注意，为了与当前的深度图像修复方法进行公平比较，我们没有在 Global&Local 中使用后处理模块。

Places365-Challenge

算法	掩膜类型	分辨率	训练集容量	测试集	l1 损失	PSNR	SSIM	下载
Global&Local	square bbox	256x256	500k	Places365-val	11.164	23.152	0.862	模型 \| 日志

CelebA-HQ

算法	掩膜类型	分辨率	训练集容量	测试集	l1 损失	PSNR	SSIM	下载
Global&Local	square bbox	256x256	500k	CelebA-val	6.678	26.780	0.904	模型 \| 日志

PConv (ECCV’2018)¶

PConv (ECCV'2018)

@inproceedings{liu2018image,
  title={Image inpainting for irregular holes using partial convolutions},
  author={Liu, Guilin and Reda, Fitsum A and Shih, Kevin J and Wang, Ting-Chun and Tao, Andrew and Catanzaro, Bryan},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  pages={85--100},
  year={2018}
}

Places365-Challenge

算法	掩膜类型	分辨率	训练集容量	测试集	l1 损失	PSNR	SSIM	下载
PConv	free-form	256x256	500k	Places365-val	8.776	22.762	0.801	模型 \| 日志

CelebA-HQ

算法	掩膜类型	分辨率	训练集容量	测试集	l1 损失	PSNR	SSIM	下载
PConv	free-form	256x256	500k	CelebA-val	5.990	25.404	0.853	模型 \| 日志